Objectives

Accurate and efficient knee cartilage and bone segmentation are necessary for basic science, clinical trial, and clinical applications. This work tested a multi-stage convolutional neural network framework for MRI image segmentation.

Materials and methods

Stage 1 of the framework coarsely segments images outputting probabilities of each voxel belonging to the classes of interest: 4 cartilage tissues, 3 bones, 1 background. Stage 2 segments overlapping sub-volumes that include Stage 1 probability maps concatenated to raw image data. Using six fold cross-validation, this framework was tested on two datasets comprising 176 images [88 individuals in the Osteoarthritis Initiative (OAI)] and 60 images (15 healthy young men), respectively.

Results

On the OAI segmentation dataset, the framework produces cartilage segmentation accuracies (Dice similarity coefficient) of 0.907 (femoral), 0.876 (medial tibial), 0.913 (lateral tibial), and 0.840 (patellar). Healthy cartilage accuracies are excellent (femoral = 0.938, medial tibial = 0.911, lateral tibial = 0.930, patellar = 0.955). Average surface distances are less than in-plane resolution. Segmentations take 91 ± 11 s per knee.

Discussion

The framework learns to automatically segment knee cartilage tissues and bones from MR images acquired with two sequences, producing efficient, accurate quantifications at varying disease severities.

中文翻译：

---

使用多阶段卷积神经网络自动进行膝关节软骨和骨骼分割：来自骨关节炎倡议的数据

目标

准确有效的膝关节软骨和骨骼分割对于基础科学、临床试验和临床应用是必要的。这项工作测试了用于 MRI 图像分割的多级卷积神经网络框架。

材料和方法

框架的第 1 阶段粗略分割图像，输出属于感兴趣类别的每个体素的概率：4 个软骨组织、3 个骨骼、1 个背景。第 2 阶段分段重叠子卷，包括连接到原始图像数据的第 1 阶段概率图。使用六折交叉验证，该框架在两个数据集上进行了测试，该数据集分别包含 176 张图像 [骨关节炎倡议 (OAI) 中的 88 个人] 和 60 张图像（15 名健康年轻男性）。

结果

在 OAI 分割数据集上，该框架产生的软骨分割精度（Dice 相似系数）为 0.907（股骨）、0.876（胫骨内侧）、0.913（胫骨外侧）和 0.840（髌骨）。健康的软骨精度非常好（股骨 = 0.938，胫骨内侧 = 0.911，胫骨外侧 = 0.930，髌骨 = 0.955）。平均表面距离小于面内分辨率。分割每个膝盖需要 91 ± 11 秒。

讨论

该框架学习从使用两个序列获取的 MR 图像中自动分割膝关节软骨组织和骨骼，在不同的疾病严重程度下产生有效、准确的量化。